Simple thoughts on building, designing, and shipping.
Citrini Research's 2028 macro scenario makes a chilling case: the more AI succeeds, the worse the economy gets. An analysis of Ghost GDP, the Intelligence Displacement Spiral, and why optimism itself may be the risk.
Three companies updated their coding agents at the same time. The directions overlap. The real battleground isn't models; it's how fast they absorb developer workflows.
From the SaaSpocalypse to model-specific silicon, five bold predictions for where AI is heading in 2026, with roughly 50% confidence of getting them right.
My API costs jumped 10x when the cache broke in production. The same day, Anthropic engineers explained exactly why.
Google Research validated it across 7 models and 7 benchmarks. No training, no prompt engineering. Just copy-paste. I tested it and here's what actually happened.
What LangChain's Terminal Bench results and the hashline format experiment revealed. The same model flipped leaderboard rankings, and the reasons came down to three things: prompts, tools, and middleware.
From Cloudflare and Vercel's Markdown for Agents to Google's WebMCP, reading and writing are being standardized simultaneously, ushering in the Agent-Native Web era.
Five SKILL.md body writing principles buried in Anthropic's official documentation. From separating description and body roles to embedding verification loops.
Korea-exclusive KakaoTalk promotion offers ChatGPT Pro at 29,000 KRW instead of $220/month, plus the new Codex-5.3-Spark delivers 1,000 tokens per second.
The real competitive edge in the agent era isn't the model - it's filesystem design. Here's how to unify your company's data into one namespace.
Every connection matters to me.
Feel free to reach out anytime.